Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the safe-read profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower, and the description still adds meaningful behaviour: copy over `max` is refused by every writing tool, and an unfilled slot renders a raw token like `text_a1b2c3` at whatever size the design paints it. Those are real consequences an agent could not derive from the annotations, though nothing is said about result size, pagination, or lookup failure when kind/variant don't resolve.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose ('What copy a template needs, slot by slot') and then layered into the slot taxonomy, sizing rule, slot-matching rule, and the failure mode. The capitalized emphasis and em-dash cadence are heavy but each sentence carries distinct instruction; the one cost is length for a two-parameter read tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-shape burden and does so well, enumerating the per-slot fields (`for`, position like 'plans 2 of 3', sample copy, `max`) and the safe-write rule. Nothing needed to interpret the response before writing copy is missing; only the input side (kind/variant) is thin.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%: `variant` is documented in the schema as a layout id, but `kind` has no description anywhere. The prose never mentions either parameter, so it contributes zero meaning beyond the schema and leaves half the required inputs (including the required `kind`) unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource: the per-slot copy requirements of a template (slot names, positions, sample copy, max characters). It is specific about what is returned ('WHAT EACH SLOT IS ... and WHERE IT SITS ... plus the template's sample copy and the MOST CHARACTERS it takes'), but it never states a verb for the tool itself or contrast it against near-neighbours like uichemy_get_template_code or uichemy_describe_sections, so the agent must infer its distinctness.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is unusually explicit: 'READ THIS BEFORE WRITING COPY', 'fill every slot', 'Write to about the sample's length', and 'put each piece of copy in the slot whose `for` matches it'. That is clear when-to-use guidance with concrete operating rules, though it names no alternative tool or a when-not-to-use condition, so the routing burden stays on the caller.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.